English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Classification of time series data is an important task for many applicationdomains. One of the best existing methods for this task, in terms of accuracyand computation time, is MiniROCKET. In this work, we extend this approach toprovide better global temporal encodings using hyperdimensional computing (HDC)mechanisms. HDC (also known as Vector Symbolic Architectures, VSA) is a generalmethod to explicitly represent and process information in high-dimensionalvectors. It has previously been used successfully in combination with deepneural networks and other signal processing algorithms. We argue that theinternal high-dimensional representation of MiniROCKET is well suited to becomplemented by the algebra of HDC. This leads to a more general formulation,HDC-MiniROCKET, where the original algorithm is only a special case. We willdiscuss and demonstrate that HDC-MiniROCKET can systematically overcomecatastrophic failures of MiniROCKET on simple synthetic datasets. These resultsare confirmed by experiments on the 128 datasets from the UCR time seriesclassification benchmark. The extension with HDC can achieve considerablybetter results on datasets with high temporal dependence without increasing thecomputational effort for inference.

HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing